Answer 415 for a source whose first bytes do not match its Content-Type (closes #253)

A body whose first bytes are not those of the format its Content-Type
names answered 500 on both image routes, was logged as pixa's own
error, and was fetched again on every request. Both routes now answer
415 for each error the first-bytes check returns, and the image service
logs the refused source at warning level. The failure also gets a
negative cache entry, as an upstream error status does, so the source
URL is not fetched for 5 minutes and answers 502 meanwhile. README.md
says so.

TestService_Get_ConcurrentMissesShareAFailure still expects such a
source to be fetched again and fails until its case is changed.

Model: opus-5-5

internal/handlers/image.go

@@ -15,6 +15,7 @@ import (
 	"sneak.berlin/go/pixa/internal/httpfetcher"
 	"sneak.berlin/go/pixa/internal/imageprocessor"
 	"sneak.berlin/go/pixa/internal/imgcache"
+	"sneak.berlin/go/pixa/internal/magic"
 )
 
 // HandleImage handles the main image proxy route:
@@ -220,6 +221,18 @@ func (s *Handlers) HandleTooManyRequests() http.HandlerFunc {
 func (s *Handlers) respondImageError(
 	w http.ResponseWriter, req *imgcache.ImageRequest, err error,
 ) {
+	// An upstream body whose first bytes are not those of the format its
+	// Content-Type names is the upstream's error, not pixa's: the image
+	// service has logged it as a refused source.
+	if errors.Is(err, magic.ErrMagicByteMismatch) ||
+		errors.Is(err, magic.ErrUnknownFormat) ||
+		errors.Is(err, magic.ErrNotEnoughData) {
+		s.respondError(w, "unsupported source format",
+			http.StatusUnsupportedMediaType)
+
+		return
+	}
+
 	s.log.Error("failed to get image",
 		"host", req.SourceHost,
 		"path", req.SourcePath,

internal/handlers/imageenc.go

@@ -15,6 +15,7 @@ import (
 	"sneak.berlin/go/pixa/internal/httpfetcher"
 	"sneak.berlin/go/pixa/internal/imageprocessor"
 	"sneak.berlin/go/pixa/internal/imgcache"
+	"sneak.berlin/go/pixa/internal/magic"
 )
 
 // HandleImageEnc handles requests to /v1/e/{token}/* for encrypted
@@ -162,7 +163,10 @@ func (s *Handlers) handleImageError(w http.ResponseWriter, err error) {
 		s.respondError(w, "server busy, try again later",
 			http.StatusServiceUnavailable)
 	case errors.Is(err, httpfetcher.ErrInvalidContentType),
-		errors.Is(err, imageprocessor.ErrUnsupportedInputFormat):
+		errors.Is(err, imageprocessor.ErrUnsupportedInputFormat),
+		errors.Is(err, magic.ErrMagicByteMismatch),
+		errors.Is(err, magic.ErrUnknownFormat),
+		errors.Is(err, magic.ErrNotEnoughData):
 		s.respondError(w, "unsupported source format",
 			http.StatusUnsupportedMediaType)
 	case errors.Is(err, imageprocessor.ErrOutputTooLarge):

internal/imgcache/service.go

@@ -438,13 +438,7 @@ func (s *Service) fetchAndProcess(
 	if err != nil {
 		// Store negative cache for certain errors
 		if isNegativeCacheable(err) {
-			statusCode := extractStatusCode(err)
-
-			storeErr := s.cache.StoreNegative(ctx, req, statusCode, err.Error())
-			if storeErr != nil {
-				s.log.Warn("failed to store negative cache entry",
-					"host", req.SourceHost, "path", req.SourcePath, "error", storeErr)
-			}
+			s.storeNegative(ctx, req, extractStatusCode(err), err)
 		}
 
 		return nil, fmt.Errorf("upstream fetch failed: %w", err)
@@ -490,9 +484,16 @@ func (s *Service) fetchAndProcess(
 		"cipher", fetchResult.TLSCipherSuite,
 	)
 
-	// Validate magic bytes match content type
+	// Validate magic bytes match content type. A body that does not is the
+	// upstream's error, so it gets a negative cache entry, as an upstream
+	// error status does.
 	err = magic.ValidateMagicBytes(sourceData, fetchResult.ContentType)
 	if err != nil {
+		s.log.Warn("source refused", "request_id", middleware.GetReqID(ctx),
+			"host", req.SourceHost, "path", req.SourcePath,
+			"content_type", fetchResult.ContentType, "error", err)
+		s.storeNegative(ctx, req, httpStatusUnsupportedMediaType, err)
+
 		return nil, fmt.Errorf("content validation failed: %w", err)
 	}
 
@@ -508,6 +509,19 @@ func (s *Service) fetchAndProcess(
 	)
 }
 
+// storeNegative stores a negative cache entry for req's source, whose fetch
+// failed with err, so the source is not fetched again until the entry
+// expires. A failure to store the entry is only logged.
+func (s *Service) storeNegative(
+	ctx context.Context, req *ImageRequest, statusCode int, err error,
+) {
+	storeErr := s.cache.StoreNegative(ctx, req, statusCode, err.Error())
+	if storeErr != nil {
+		s.log.Warn("failed to store negative cache entry",
+			"host", req.SourceHost, "path", req.SourcePath, "error", storeErr)
+	}
+}
+
 // processedVariant is a variant as processAndStore made it. Each request that
 // shared its processing serves it through a reader of its own.
 type processedVariant struct {
@@ -616,8 +630,9 @@ func signatureRequest(req *ImageRequest) *signature.Request {
 
 // HTTP status codes for error responses.
 const (
-	httpStatusBadGateway    = 502
-	httpStatusInternalError = 500
+	httpStatusBadGateway           = 502
+	httpStatusInternalError        = 500
+	httpStatusUnsupportedMediaType = 415
 )
 
 // isNegativeCacheable returns true if the error should be cached.